A method, system, device, medium and product for identifying a habitable region of Mars based on a SOM algorithm

Abstract

This application discloses a method, system, device, medium, and product for identifying habitable regions on Mars based on the SOM algorithm, relating to the field of habitable region identification on Mars. The method includes: collecting multi-source geological element layers on Mars related to the multidimensional origin of life; calculating the information entropy of each element in the multi-source geological element layers; quantifying the information value of each geological element layer based on the information entropy, and optimizing the element weights by combining expert prior constraints to determine expert constraint entropy weights; using the SOM algorithm, constructing an SOM network based on the expert constraint entropy weights and the multi-source geological element layers to generate a suitability probability map; and identifying habitable regions based on the suitability probability map. This application can identify habitable regions with high accuracy and objectivity.

Description

Technical Field

[0001] This application relates to the field of Martian habitable region identification, and in particular to a method, system, device, medium, and product for identifying Martian habitable regions based on the SOM algorithm. Background Technology

[0002] Suitability assessment is a core technical means for exploring the origin of life and identifying habitable environments. Its core lies in integrating multi-dimensional geological elements and quantifying the synergistic relationships between these elements. Currently, suitability assessment methods mostly rely on qualitative analysis of single elements, expert experience weighting, or simple layer overlay, which have significant technical limitations. 1) Traditional assessment methods are difficult to capture the complex nonlinear relationships between multi-source geological elements (such as mineral distribution, geomorphological features, and geological units), are greatly influenced by subjective experience, and have insufficient accuracy and objectivity in the assessment results; 2) Existing technologies lack the quantitative utilization of element information entropy, and cannot allocate reasonable weights based on the data dispersion and information value of each layer, resulting in the underestimation or overestimation of the contribution of key livable elements. 3) The layer integration process did not take into account the prior constraints of experts, making it difficult to meet the element priority requirements under specific geological scenarios, and it lacked an automated consistency verification mechanism, making it impossible to effectively verify the fit between the evaluation results and the basic geological data. 4) The assessment results are mostly presented in two-dimensional planar form, lacking three-dimensional spatial constraints and dynamic visualization, making it difficult to support habitability analysis in deep or complex geological environments.

[0003] While existing self-organizing map (SOM) algorithms can uncover potential relationships in cluster analysis, they lack the integration of entropy weight optimization and expert constraints, resulting in insufficient relevance for suitability assessment. Furthermore, most assessment processes fail to form a closed loop of "modeling-output-verification," making it difficult to guarantee the reliability of suitability region identification results. Therefore, there is an urgent need to develop a high-precision life suitability assessment technology that integrates information entropy quantification, expert constraint guidance, three-dimensional spatial representation, and automated verification. Summary of the Invention

[0004] The purpose of this application is to provide a method, system, device, medium, and product for identifying habitable regions on Mars based on the SOM algorithm, so as to solve the problem of low reliability of habitable region identification results.

[0005] To achieve the above objectives, this application provides the following solution: Firstly, this application provides a method for identifying habitable regions on Mars based on the SOM algorithm, including: Collect multi-source geological feature layers on Mars that are related to the multidimensional origin of life; Calculate the information entropy of each element in the multi-source geological element layer; The information value of each geological element layer is quantified based on the information entropy, and the element weights are optimized by combining expert prior constraints to determine the expert constraint entropy weights. Using the SOM algorithm, an SOM network is constructed based on the expert-constrained entropy weights and the multi-source geological element layers to generate a suitability probability map; Habitable areas are identified based on the suitability probability map.

[0006] Secondly, this application provides a Martian habitable region identification system based on the SOM algorithm, comprising: The layer acquisition module is used to acquire multi-source geological element layers on Mars that are related to the multidimensional origin of life. The information entropy calculation module is used to calculate the information entropy of each element in the multi-source geological element layer; The expert-constrained entropy weight determination module is used to quantify the information value of each geological element layer based on the information entropy, and combine it with expert prior constraints to optimize the element weights and determine the expert-constrained entropy weights. The suitability probability map generation module is used to construct an SOM network based on the expert-constrained entropy weights and the multi-source geological element layers using the SOM algorithm, and generate a suitability probability map. The Mars habitable region identification module based on the SOM algorithm is used to identify habitable regions according to the suitability probability map.

[0007] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method for identifying habitable regions on Mars based on the SOM algorithm.

[0008] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method for identifying habitable regions on Mars based on the SOM algorithm.

[0009] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method for identifying habitable regions on Mars based on the SOM algorithm.

[0010] According to the specific embodiments provided in this application, this application has the following technical effects: This application collects multi-source geological element layers on Mars related to the multidimensional origin of life, calculates the information entropy of each element in the multi-source geological element layers, quantifies the information value of each geological element layer, and optimizes the element weights by combining expert prior constraints to determine the expert-constrained entropy weights. This approach balances data objectivity and geological regularity, solving the problem of subjective weight allocation in traditional methods. It utilizes the Self-Organizing Feature Map (SOM) algorithm to mine nonlinear relationships between multiple elements, constructing an SOM network. This overcomes the limitation of simple layer overlay in resolving complex collaborative relationships, improving the accuracy of suitability assessment. By generating a suitability probability map, it achieves three-dimensional visualization and reliability verification of the assessment results, providing technical support for habitability analysis of deep or complex geological environments. This application, through the organic combination of information entropy quantification, expert prior constraint guidance, SOM algorithm modeling, and three-dimensional spatial representation, identifies habitable areas with high precision and objectivity. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 A flowchart illustrating a method for identifying habitable regions on Mars based on the SOM algorithm, provided in an embodiment of this application; Figure 2 A technical roadmap for a method for identifying habitable regions on Mars based on the SOM algorithm, provided in one embodiment of this application; Figure 3 This is a schematic diagram of multi-source geological element layer preprocessing provided in an embodiment of this application; Figure 4 A suitability probability diagram provided for an embodiment of this application. Detailed Implementation

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0014] To make the objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0015] like Figure 1 As shown in the figure, this application provides a method for identifying habitable regions on Mars based on the SOM algorithm, including: S1: Collect multi-source geological feature layers on Mars related to the multidimensional origin of life.

[0016] S2: Calculate the information entropy of each element in the multi-source geological element layer.

[0017] S3: Quantify the information value of each geological element layer based on the information entropy, and optimize the element weights by combining expert prior constraints, and determine the expert constraint entropy weights.

[0018] S4: Using the SOM algorithm, construct an SOM network based on the expert-constrained entropy weights and the multi-source geological element layers to generate a suitability probability map.

[0019] S5: Identify habitable areas based on the suitability probability map.

[0020] like Figure 2 As shown, this application presents a complete site selection assessment process for the habitability of celestial life, which is divided into three major stages: preliminary preparation and indicator determination, core modeling and site selection optimization, and result verification and implementation.

[0021] In the preliminary preparation and indicator determination phase, the mission objectives were first identified, and seven core elements related to the origin of life were decomposed. After sorting out the basic indicators, the core indicators were optimized and screened by combining expert constraints and Bayesian optimization. Moving into the core modeling and site selection optimization phase, multi-source geological data underwent standardized preprocessing, including unifying the format and eliminating dimensions. Then, a model was built based on the SOM algorithm. Two-stage weight optimization (entropy weight calculation + expert constraints) and spatial attention factors were used to address the pain points of Mars data, quantifying the synergistic relationships of multiple elements, completing suitability assessment and initial screening of candidate areas, and finally generating a two-dimensional suitability probability map, supplemented by a three-dimensional model to enhance spatial intuitiveness. In the results verification and implementation phase, the reliability of the results was evaluated through internal consistency verification, positive point verification, and external verification. The algorithm architecture was upgraded and iteratively optimized to address the core defects discovered during verification, ultimately determining reliable candidate areas for habitable life.

[0022] In an exemplary embodiment, the multi-source geological element layer includes a core geological element layer and a basic verification layer; the core geological element layer includes a monohydrated sulfate layer, a geological unit scoring layer, a multihydrated sulfate layer, a hydrated aluminosilicate layer, a layer with distance from dark layered yardangs, a layer with distance from alluvial fans, a layer with distance from polygons, a layer with distance from river valley networks, a layer with distance from ridge landforms, a layer with distance from deeply incised river valleys, a layer with distance from foliated features, a hydrothermal mineral layer, and a layer of iron-magnesium layered silicates; the basic verification layer, used for consistency verification, includes a geological evolution layer, a paleoclimate layer, a water activity layer, a hydrothermal activity layer, a layer on the origin of life, a layer on reproductive water bodies, and a layer on preservation carriers.

[0023] In practical applications, the data format requirements are as follows: all layers must be in Tagged Image File Format (TIFF), containing complete coordinate system information (such as the World Geodetic System 1984 (WGS84 coordinate system), and the spatial resolution must be uniformly adjusted to the target size (default 800×500 pixels).

[0024] In one exemplary embodiment, S2 further includes: S11: Using a conversion tool, the multi-source geological element layers are unified into the target coordinate system, and all multi-source geological element layers are clipped with the boundary of the study area as a constraint.

[0025] S12: Based on the cropped multi-source geological element layer, perform positive transformation on negative influencing elements to determine the positively transformed influencing elements.

[0026] S13: Convert the positive influencing factors and the corresponding factor values ​​of the positively influenced factors into quantitative indicators that are positively correlated with suitability.

[0027] S14: Normalize the quantitative indicators and fill in the missing values ​​in the multi-source geological element layer to determine the preprocessed multi-source geological element layer.

[0028] In practical applications, Figure 3This paper presents the standardized preprocessing workflow for multi-source geological element layers in this application. For two typical types of data, the transformation from raw data to standardized features was completed: For vector geomorphic data such as river valley networks, the original distance from each sampling point to the river valley network was first calculated from the original vector map, generating a distance heatmap in kilometers. Then, standardization was applied to map the original distances to the 0-1 interval, eliminating dimensional differences and obtaining a standardized distance layer that can be directly used for modeling. For binary mineral data such as iron-magnesium layered silicates, the spatial distribution of mineral points was first extracted from the original binary map, then the density of mineral points was calculated to generate a density heatmap. Finally, the density values ​​were standardized to the 0-1 interval, obtaining a standardized density layer reflecting the degree of mineral enrichment. The entire process uniformly transforms raw geological data of different types and dimensions into standardized features in the 0-1 interval, eliminating dimensional differences between data while preserving the spatial distribution characteristics of elements, providing reliable input for subsequent entropy weight calculation and SOM modeling.

[0029] To ensure data consistency and usability, a unified preprocessing procedure is performed on multi-source geological element layers. The process is as follows: Coordinate System 1: Use projection transformation tools to unify all layers to the target coordinate system (such as UTM (Universal Transverse Mercator) projection) to eliminate coordinate deviations.

[0030] Spatial extent clipping: All layers are clipped using the study area boundary as a constraint to ensure a consistent evaluation range. The clipping boundary is defined through a vector boundary file.

[0031] Data forwarding: Positively influencing elements (mineral layers and geological unit layers) are left unprocessed, while negatively influencing elements (distance-based layers) are forwarded. The element values ​​are converted into quantitative indicators that are positively correlated with life suitability. , These are the original and maximum values ​​of the data in this layer, respectively. These are the influencing factors after positive transformation.

[0032] Normalization: Normalize the data in each layer within the range [0,1] to eliminate dimensional differences. The calculation formula is as follows: in, This is the minimum value of the data in this layer. For the normalized data, .

[0033] Missing value imputation: Bilinear interpolation is used to imput missing values ​​(Not a Number, NaN) in the layer to ensure data integrity.

[0034] In an exemplary embodiment, S3 specifically includes: S31: Calculate the initial entropy weight based on the information entropy.

[0035] S32: Determine the weight constraint range of key elements based on the geological laws governing the origin of life.

[0036] S33: Construct a least-squares optimization objective function based on the initial entropy weights.

[0037] S34: Under the weight constraint range and the equality constraint that the weight sum is 1, solve the least squares optimization objective function and determine the expert constraint entropy weight.

[0038] In practical applications, a dual weight allocation mechanism of "information entropy quantification - expert constraint optimization" is constructed, and the specific steps are as follows: 1) Information Entropy Calculation: Based on the data of each standardized layer, the information entropy of each element is calculated to quantify the data dispersion and information value. The entropy calculation formula is as follows: in, n The number of data intervals. Let be the probability of the i-th data interval. For the first k The information entropy of each element is such that the lower the entropy value, the higher the concentration of the data and the greater the information value.

[0039] 2) Initial Entropy Weight Generation: Initial weights are calculated based on information entropy. The lower the entropy value, the greater the weight. The weight normalization formula is as follows: in, m The number of multi-source geological feature layers, As the initial entropy weight, For the first k Information entropy of each element.

[0040] 3) Expert Constraint Definition: Based on the geological laws governing the origin of life, the weight constraints of key elements are set as shown in Table 1 to ensure that the contribution of core habitable elements conforms to geological a priori knowledge. Among them, the geological laws governing the origin of life are the core scientific consensus of the academic community on the geological conditions required for the birth of early life. Its core revolves around the necessary foundations for the formation and survival of life: liquid water is the primary prerequisite. It is not only a solvent for organic chemical reactions, but also maintains a mild environment to protect life substances; geological carriers such as mineral surfaces (such as layered silicates) can serve as catalytic interfaces to promote the synthesis of small organic molecules from inorganic substances, while sedimentary environments (such as alluvial fans and river valleys) can enrich essential elements for life such as carbon and nitrogen; the environment needs to have a mild energy supply (such as redox reactions at the mineral-water interface) and avoid extreme conditions (such as high temperatures from strong hydrothermal fluids), while relying on hydrodynamic processes and stable structures to achieve material cycling and maintain environmental stability.

[0041] Table 1 Key Element Weight Constraint Table

[0042] 4) Weight Optimization Solution: Based on the initial entropy weights, construct a least-squares optimization objective function. Under the constraints of the weight range and the equality constraint that "the sum of the weights is 1", solve for the optimal weights, i.e., the expert-constrained entropy weights. Objective function: Constraints: (Expert hard constraints) (Normalization constraint) in, k This refers to the layer number of the multi-source geological elements; The optimal expert-constrained entropy weight for the k-th type of geological element; Let be the initial entropy weight for the k-th type of geological element; This represents the lower limit of the weight of the k-th type of geological element; This represents the upper limit of the weight of the k-th type of geological element.

[0043] The optimization problem is solved using the Sequential Least Squares Programming (SLSQP) algorithm to obtain the optimal weights that satisfy the constraints. w opt .

[0044] In an exemplary embodiment, S4 specifically includes: S41: Standardize the core geological element layer in the multi-source geological element layer to determine the standardized core geological element layer.

[0045] S42: Flatten the standardized core geological element layer into a two-dimensional data matrix.

[0046] S43: Using the SOM algorithm, construct an m×m neuron SOM network and set the model parameters; m is the hyperparameter of the SOM network.

[0047] S44: Based on the model parameters, the two-dimensional data matrix and the expert constraint entropy weights are used as inputs to the SOM network. A Gaussian neighborhood function is used to train and optimize the neuron weights in batches, so that the neurons match the feature distribution of the input data; the input data includes the two-dimensional data matrix and the expert constraint entropy weights.

[0048] S45: Calculate the mean of all input data corresponding to each neuron across each element dimension to generate a neuron-element mean matrix; the neuron-element mean matrix is ​​used to reflect the combined feature of the elements represented by the neuron.

[0049] S46: Calculate the suitability score for each neuron based on the tensor product of the neuron-feature mean matrix and the expert constraint entropy weight.

[0050] S47: Based on the best matching neuron corresponding to each input data, map the suitability score to a spatial grid to generate a suitability probability map.

[0051] In practical applications, a clustering model (i.e., a SOM network) is constructed using the SOM algorithm based on optimized weights (i.e., expert-constrained entropy weights). This step uses a standardized two-dimensional data matrix of 13 geological elements (pixel count × element count) and optimized expert-constrained entropy weights as core inputs. First, an n×n neuron SOM network is initialized. Through batch iterative training, the neuron weights are matched to the feature distribution of the input data. Nonlinear synergistic relationships between different geological elements are explored during unsupervised learning. Then, based on the training results, the life suitability score of each neuron is calculated, and pixels are mapped to their best-matching neuron (BMU). Finally, a two-dimensional life suitability probability map stored in TIFF format is output. The pixel values ​​(ranging from 0 to 1) of this probability map directly represent the habitability potential of the corresponding spatial location. In short, the evaluation is completed in a closed loop, following the logical progression of "data collection - standardization - weight optimization - modeling and prediction - verification".

[0052] In practical applications, S4 specifically manifests as the following steps: Data dimensionality reduction and sampling: The standardized 13-category feature layers are flattened into a two-dimensional data matrix (number of pixels × number of features). To avoid memory overflow, the large dataset is randomly downsampled (maximum number of pixels 500,000).

[0053] SOM Network Initialization and Training: Construct an n×n (default 15×15) SOM network with an initial learning rate of 0.3 and a neighborhood radius of 1.0. Use a Gaussian neighborhood function and optimize the neuron weights through batch training (5000 iterations) to match the feature distribution of the input data with the neurons.

[0054] Node mean calculation: For each neuron, calculate the mean of all its corresponding pixels across each feature dimension to generate a neuron-feature mean matrix, which reflects the feature combination characteristics represented by the neuron.

[0055] Suitability quantification: The life fitness score of each neuron is calculated by the tensor product of the optimal weights and the neuron mean matrix, as shown in the following formula: in, Let (i,j) be the fitness score of the (i,j)th neuron. For the (i,j)th neuron in the first... k The mean of each element; The optimal entropy weight is determined by expert constraints for k-type geological elements.

[0056] Probabilistic map generation: Based on the best-matching neuron corresponding to each pixel, the neuron fitness score is mapped to a spatial grid to generate a life fitness probability map. The probability value ranges from [0,1], with higher values ​​indicating stronger life fitness. Figure 4 As shown.

[0057] Figure 4 This paper presents two visualizations of the Mars habitability probability map generated in this application: the left side is a two-dimensional planar view, using latitude and longitude coordinates and a color gradient from red to green to intuitively present the habitability potential of each spatial location within the study area (red represents high probability, green represents low probability), clearly reflecting the planar distribution of habitability; the right side is a three-dimensional view overlaid with elevation information, which, while retaining color coding, shows the coupling relationship between habitability and topography through terrain undulations, such as the spatial correlation between red high-habitability areas and specific landforms, further revealing the spatial distribution characteristics of habitability under the synergistic effect of geological elements. The two views complement each other, providing multi-dimensional and intuitive basis for subsequent candidate area selection.

[0058] In practical applications, S4 is followed by automatic consistency verification.

[0059] Establish a consistency verification mechanism between the assessment results and the basic geological layers to quantify the reliability of the assessment results. If the automatic consistency verification results show that the assessment results are unreliable, targeted optimization and adjustments are required: First, review the data quality of the multi-source geological layers, fill in missing values, correct abnormal data, and re-standardize the data; second, adjust the expert constraint range or weight optimization parameters in conjunction with the geological laws of the origin of life, and optimize the core parameters such as the number of neurons and the number of iterations in the SOM model; if necessary, supplement the key geological element layers and re-execute the "weight optimization - modeling prediction - consistency verification" process until the assessment results reach the reliable standard.

[0060] Automatic consistency verification includes the following steps.

[0061] 1) Threshold determination: The percentile method is used to determine the high and low thresholds (30th percentile for low threshold and 70th percentile for high threshold) of the suitability probability map and the 7 basic layers.

[0062] 2) Pixel sampling: Randomly sample (default 1000 pixels) in the high probability area (≥ high threshold) and low probability area (≤ low threshold) of the suitability probability map to obtain the corresponding value of the pixel on each base layer; 3) Consistency Score: Define a consistency score index to quantify the degree of matching between high-suitability areas and high-value areas in the base layer, and between low-suitability areas and low-value areas in the base layer. in, The proportion of highly suitable pixels falling in the high-value area of ​​the base layer. The proportion of low-suitability pixels falling in the low-value area of ​​the base layer. , The score range is [-2, 2], and the higher the score, the stronger the consistency.

[0063] 4) Result determination: Calculate the overall average consistency score and the individual scores of each basic layer. If the overall score is >0.3, it is determined as "excellent evaluation", 0 < overall score ≤0.3 is determined as "good evaluation", and ≤0 is determined as "poor evaluation", and output the verification report.

[0064] This application provides a Martian habitable zone identification system based on the SOM algorithm, including: The layer acquisition module is used to acquire multi-source geological feature layers on Mars that are related to the multidimensional origin of life.

[0065] The information entropy calculation module is used to calculate the information entropy of each element in the multi-source geological element layer.

[0066] The expert-constrained entropy weight determination module is used to quantify the information value of each geological element layer based on the information entropy, and combine it with expert prior constraints to optimize the element weights and determine the expert-constrained entropy weights.

[0067] The suitability probability map generation module is used to construct an SOM network based on the expert-constrained entropy weights and the multi-source geological element layers using the SOM algorithm, and generate a suitability probability map.

[0068] The Mars habitable region identification module based on the SOM algorithm is used to identify habitable regions according to the suitability probability map.

[0069] This application achieves high-precision and objective assessment of life suitability by organically combining information entropy quantification, expert constraint guidance, SOM algorithm modeling, and three-dimensional spatial representation. Compared with traditional technologies, it has the following advantages: 1. An innovative entropy constraint mechanism is introduced, which allocates weights based on the value of data information. At the same time, it combines expert prior constraints, taking into account both the objectivity of data and the regularity of geological patterns, and solves the problem of subjective weight allocation in traditional methods.

[0070] 2. By utilizing the SOM algorithm to mine nonlinear relationships among multiple elements, the limitations of simple layer overlay in resolving complex collaborative relationships are overcome, thus improving the accuracy of suitability assessment.

[0071] 3. A closed-loop process of "two-dimensional assessment - three-dimensional modeling - automatic verification" was constructed, realizing three-dimensional visualization and reliability verification of assessment results, and providing technical support for habitability analysis of deep or complex geological environments.

[0072] 4. The entire process is highly automated, covering data preprocessing, modeling, verification, and output, which greatly reduces human intervention and improves evaluation efficiency. It can be widely used in planetary geological exploration, research on the origin of early life on Earth, and other fields.

[0073] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments. The computer device can be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, memory, and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device stores data to be processed. The I / O interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with an external terminal via a network connection. When the computer program is executed by the processor, it implements the above-described methods.

[0074] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0075] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0076] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0077] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by hardware related to computer program instructions. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0078] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0079] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0080] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for identifying habitable regions on Mars based on the SOM algorithm, characterized in that, include: Collect multi-source geological feature layers on Mars that are related to the multidimensional origin of life; Calculate the information entropy of each element in the multi-source geological element layer; The information value of each geological element layer is quantified based on the information entropy, and the element weights are optimized by combining expert prior constraints to determine the expert constraint entropy weights. Using the SOM algorithm, an SOM network is constructed based on the expert-constrained entropy weights and the multi-source geological element layers to generate a suitability probability map; Habitable areas are identified based on the suitability probability map.

2. The method for identifying habitable regions on Mars based on the SOM algorithm according to claim 1, characterized in that, The multi-source geological feature layer includes a core geological feature layer and a basic verification layer; The core geological element layers include a monohydrated sulfate layer, a geological unit scoring layer, a semihydrated sulfate layer, a hydrated aluminosilicate layer, a layer with distance from dark layered yardangs, a layer with distance from alluvial fans, a layer with distance from polygons, a layer with distance from river valley networks, a layer with distance from ridge landforms, a layer with distance from deeply incised river valleys, a layer with distance from foliated features, a hydrothermal mineral layer, and an iron-magnesium layered silicate layer. The basic verification layers include a geological evolution layer, a paleoclimate layer, a water activity layer, a hydrothermal activity layer, a life origin layer, a reproductive water body layer, and a preservation carrier layer.

3. The method for identifying habitable regions on Mars based on the SOM algorithm according to claim 1, characterized in that, Calculating the information entropy of each feature in the multi-source geological feature layer, prior to which the following steps are also included: A conversion tool was used to unify the multi-source geological element layers into the target coordinate system, and all multi-source geological element layers were clipped with the boundary of the study area as a constraint. Based on the cropped multi-source geological element layer, the negative influencing elements are positiveized to determine the positiveized influencing elements. The positive influencing factors and the corresponding factor values ​​of the positively converted influencing factors are converted into quantitative indicators that are positively correlated with suitability. The quantitative indicators are normalized and missing values ​​in the multi-source geological element layer are filled to determine the preprocessed multi-source geological element layer.

4. The method for identifying habitable regions on Mars based on the SOM algorithm according to claim 1, characterized in that, Information entropy for: in, n The number of data intervals. For the first i The probability of a data interval.

5. The method for identifying habitable regions on Mars based on the SOM algorithm according to claim 1, characterized in that, By combining the expert prior constraints with the optimization element weights, the expert constraint entropy weights are determined, specifically including: Calculate the initial entropy weight based on the information entropy; Based on the geological laws governing the origin of life, determine the weight constraints of key elements; Based on the initial entropy weights, a least squares optimization objective function is constructed; Under the weight constraint range and the equality constraint that the weight sum is 1, solve the least squares optimization objective function and determine the expert constraint entropy weight.

6. The method for identifying habitable regions on Mars based on the SOM algorithm according to claim 1, characterized in that, Using the SOM algorithm, an SOM network is constructed based on the expert-constrained entropy weights and the multi-source geological element layers to generate a suitability probability map, specifically including: The core geological element layer in the multi-source geological element layer is standardized to determine the standardized core geological element layer. Flatten the standardized core geological element layer into a two-dimensional data matrix; Using the SOM algorithm, an m×m neuron SOM network is constructed, and the model parameters are set; m is the hyperparameter of the SOM network. Based on the model parameters, the two-dimensional data matrix and the expert constraint entropy weights are used as inputs to the SOM network. A Gaussian neighborhood function is used to train and optimize the neuron weights in batches, so that the neurons match the feature distribution of the input data. The input data includes the two-dimensional data matrix and the expert constraint entropy weights. The mean values ​​of all input data corresponding to each neuron are calculated across each feature dimension to generate a neuron-feature mean matrix; the neuron-feature mean matrix is ​​used to reflect the feature combination characteristics of the features represented by the neuron; The suitability score of each neuron is calculated based on the tensor product of the neuron-feature mean matrix and the expert constraint entropy weight. Based on the best matching neuron corresponding to each input data, the suitability score is mapped to a spatial grid to generate a suitability probability map.

7. A Martian habitable zone identification system based on the SOM algorithm, characterized in that, The Mars habitable region identification system based on the SOM algorithm executes the Mars habitable region identification method based on the SOM algorithm according to any one of claims 1-6, wherein the Mars habitable region identification system based on the SOM algorithm comprises: The layer acquisition module is used to acquire multi-source geological element layers on Mars that are related to the multidimensional origin of life. The information entropy calculation module is used to calculate the information entropy of each element in the multi-source geological element layer; The expert-constrained entropy weight determination module is used to quantify the information value of each geological element layer based on the information entropy, and combine it with expert prior constraints to optimize the element weights and determine the expert-constrained entropy weights. The suitability probability map generation module is used to construct an SOM network based on the expert-constrained entropy weights and the multi-source geological element layers using the SOM algorithm, and generate a suitability probability map. The Mars habitable region identification module based on the SOM algorithm is used to identify habitable regions according to the suitability probability map.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the Mars habitable zone identification method based on the SOM algorithm according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the method for identifying habitable regions on Mars based on the SOM algorithm as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the method for identifying habitable regions on Mars based on the SOM algorithm as described in any one of claims 1-6.

Images